CobraMamba/mamba-gpt-3b
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: CobraMamba/mamba-gpt-3b
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-29 09:18:15 +08:00
commit adbda30c26
10 changed files with 407 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
.gitattributes vendored Normal file
View File

@@ -0,0 +1,34 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text

230
README.md Normal file
View File

@@ -0,0 +1,230 @@
---
language:
- en
library_name: transformers
tags:
- gpt
- llm
- large language model
inference: false
thumbnail: >-
https://h2o.ai/etc.clientlibs/h2o/clientlibs/clientlib-site/resources/images/favicon.ico
license: apache-2.0
---
# Model Card
## Github
https://github.com/chi2liu/mamba-gpt-3b
| Metric | Value |
|-----------------------|-------|
| MMLU (5-shot) | 25.3 |
| ARC (25-shot) | 40.5 |
| HellaSwag (10-shot) | 64.9 |
| TruthfulQA (0-shot) | 37.1 |
| Avg. | 42.0 |
We use state-of-the-art [Language Model Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness) to run the benchmark tests above.
## Summary
We have fine-tuned the open-lama model and surpassed the original model in multiple evaluation subtasks, making it currently the best performing 3B model with comparable performance to llama-7b
- Base model: [openlm-research/open_llama_3b](https://huggingface.co/openlm-research/open_llama_3b)
## Usage
To use the model with the `transformers` library on a machine with GPUs, first make sure you have the `transformers`, `accelerate` and `torch` libraries installed.
```bash
pip install transformers==4.29.2
pip install accelerate==0.19.0
pip install torch==2.0.0
```
```python
import torch
from transformers import pipeline
generate_text = pipeline(
model="CobraMamba/mamba-gpt-3b",
torch_dtype="auto",
trust_remote_code=True,
use_fast=False,
device_map={"": "cuda:0"},
)
res = generate_text(
"Why is drinking water so healthy?",
min_new_tokens=2,
max_new_tokens=1024,
do_sample=False,
num_beams=1,
temperature=float(0.3),
repetition_penalty=float(1.2),
renormalize_logits=True
)
print(res[0]["generated_text"])
```
You can print a sample prompt after the preprocessing step to see how it is feed to the tokenizer:
```python
print(generate_text.preprocess("Why is drinking water so healthy?")["prompt_text"])
```
```bash
<|prompt|>Why is drinking water so healthy?</s><|answer|>
```
Alternatively, you can download the mamba_gpt_pipeline.py, store it alongside your notebook, and construct the pipeline yourself from the loaded model and tokenizer. If the model and the tokenizer are fully supported in the `transformers` package, this will allow you to set `trust_remote_code=False`.
```python
import torch
from mamba_gpt_pipeline import MambaGPTTextGenerationPipeline
from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained(
"CobraMamba/mamba-gpt-3b",
use_fast=False,
padding_side="left",
trust_remote_code=False,
)
model = AutoModelForCausalLM.from_pretrained(
"CobraMamba/mamba-gpt-3b",
torch_dtype="auto",
device_map={"": "cuda:0"},
trust_remote_code=False,
)
generate_text = MambaGPTTextGenerationPipeline(model=model, tokenizer=tokenizer)
res = generate_text(
"Why is drinking water so healthy?",
min_new_tokens=2,
max_new_tokens=1024,
do_sample=False,
num_beams=1,
temperature=float(0.3),
repetition_penalty=float(1.2),
renormalize_logits=True
)
print(res[0]["generated_text"])
```
You may also construct the pipeline from the loaded model and tokenizer yourself and consider the preprocessing steps:
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "CobraMamba/mamba-gpt-3b" # either local folder or huggingface model name
# Important: The prompt needs to be in the same format the model was trained with.
# You can find an example prompt in the experiment logs.
prompt = "<|prompt|>How are you?</s><|answer|>"
tokenizer = AutoTokenizer.from_pretrained(
model_name,
use_fast=False,
trust_remote_code=False,
)
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype="auto",
device_map={"": "cuda:0"},
trust_remote_code=False,
)
model.cuda().eval()
inputs = tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to("cuda")
# generate configuration can be modified to your needs
tokens = model.generate(
**inputs,
min_new_tokens=2,
max_new_tokens=1024,
do_sample=False,
num_beams=1,
temperature=float(0.3),
repetition_penalty=float(1.2),
renormalize_logits=True
)[0]
tokens = tokens[inputs["input_ids"].shape[1]:]
answer = tokenizer.decode(tokens, skip_special_tokens=True)
print(answer)
```
## Model Architecture
```
LlamaForCausalLM(
(model): LlamaModel(
(embed_tokens): Embedding(32000, 4096, padding_idx=0)
(layers): ModuleList(
(0-31): 32 x LlamaDecoderLayer(
(self_attn): LlamaAttention(
(q_proj): Linear(in_features=4096, out_features=4096, bias=False)
(k_proj): Linear(in_features=4096, out_features=4096, bias=False)
(v_proj): Linear(in_features=4096, out_features=4096, bias=False)
(o_proj): Linear(in_features=4096, out_features=4096, bias=False)
(rotary_emb): LlamaRotaryEmbedding()
)
(mlp): LlamaMLP(
(gate_proj): Linear(in_features=4096, out_features=11008, bias=False)
(down_proj): Linear(in_features=11008, out_features=4096, bias=False)
(up_proj): Linear(in_features=4096, out_features=11008, bias=False)
(act_fn): SiLUActivation()
)
(input_layernorm): LlamaRMSNorm()
(post_attention_layernorm): LlamaRMSNorm()
)
)
(norm): LlamaRMSNorm()
)
(lm_head): Linear(in_features=4096, out_features=32000, bias=False)
)
```
## Evaluation
We evaluated OpenLLaMA on a wide range of tasks using [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness). The LLaMA results are generated by running the original LLaMA model on the same evaluation metrics. We note that our results for the LLaMA model differ slightly from the original LLaMA paper, which we believe is a result of different evaluation protocols. Similar differences have been reported in [this issue of lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness/issues/443). Additionally, we present the results of GPT-J, a 6B parameter model trained on the [Pile](https://pile.eleuther.ai/) dataset by [EleutherAI](https://www.eleuther.ai/).
The original LLaMA model was trained for 1 trillion tokens and GPT-J was trained for 500 billion tokens. We present the results in the table below. OpenLLaMA exhibits comparable performance to the original LLaMA and GPT-J across a majority of tasks, and outperforms them in some tasks.
| **Task/Metric** | finetuned-GPT 3B | OpenLLaMA 3B |
| ---------------------- | -------- | ------------ |
| anli_r1/acc | **0.35** | 0.33 |
| anli_r2/acc | **0.33** | 0.32 |
| anli_r3/acc | 0.35 | 0.35 |
| arc_challenge/acc | **0.35** | 0.34 |
| arc_challenge/acc_norm | 0.37 | 0.37 |
| arc_easy/acc | **0.71** | 0.69 |
| arc_easy/acc_norm | 0.65 | 0.65 |
| boolq/acc | **0.72** | 0.66 |
| hellaswag/acc | **0.49** | 0.43 |
| hellaswag/acc_norm | 0.66 | **0.67** |
| openbookqa/acc | 0.26 | **0.27** |
| openbookqa/acc_norm | 0.40 | 0.40 |
| piqa/acc | **0.76** | 0.75 |
| piqa/acc_norm | 0.76 | 0.76 |
| record/em | 0.88 | 0.88 |
| record/f1 | 0.88 | **0.89** |
| rte/acc | 0.55 | **0.58** |
| truthfulqa_mc/mc1 | **0.27** | 0.22 |
| truthfulqa_mc/mc2 | **0.37** | 0.35 |
| wic/acc | **0.49** | 0.48 |
| winogrande/acc | **0.63** | 0.62 |
| Average | **0.53** | 0.52 |
We removed the task CB and WSC from our benchmark, as our model performs suspiciously well on these two tasks. We hypothesize that there could be a benchmark data contamination in the training set.
## Disclaimer
Please read this disclaimer carefully before using the large language model provided in this repository. Your use of the model signifies your agreement to the following terms and conditions.
- Biases and Offensiveness: The large language model is trained on a diverse range of internet text data, which may contain biased, racist, offensive, or otherwise inappropriate content. By using this model, you acknowledge and accept that the generated content may sometimes exhibit biases or produce content that is offensive or inappropriate. The developers of this repository do not endorse, support, or promote any such content or viewpoints.
- Limitations: The large language model is an AI-based tool and not a human. It may produce incorrect, nonsensical, or irrelevant responses. It is the user's responsibility to critically evaluate the generated content and use it at their discretion.
- Use at Your Own Risk: Users of this large language model must assume full responsibility for any consequences that may arise from their use of the tool. The developers and contributors of this repository shall not be held liable for any damages, losses, or harm resulting from the use or misuse of the provided model.
- Ethical Considerations: Users are encouraged to use the large language model responsibly and ethically. By using this model, you agree not to use it for purposes that promote hate speech, discrimination, harassment, or any form of illegal or harmful activities.
- Reporting Issues: If you encounter any biased, offensive, or otherwise inappropriate content generated by the large language model, please report it to the repository maintainers through the provided channels. Your feedback will help improve the model and mitigate potential issues.
- Changes to this Disclaimer: The developers of this repository reserve the right to modify or update this disclaimer at any time without prior notice. It is the user's responsibility to periodically review the disclaimer to stay informed about any changes.
By using the large language model provided in this repository, you agree to accept and comply with the terms and conditions outlined in this disclaimer. If you do not agree with any part of this disclaimer, you should refrain from using the model and any content generated by it.

25
config.json Normal file
View File

@@ -0,0 +1,25 @@
{
"_name_or_path": "openlm-research/open_llama_3b",
"architectures": [
"LlamaForCausalLM"
],
"attention_probs_dropout_prob": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_dropout_prob": 0.0,
"hidden_size": 3200,
"initializer_range": 0.02,
"intermediate_size": 8640,
"max_position_embeddings": 2048,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 26,
"pad_token_id": 0,
"rms_norm_eps": 1e-06,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.29.2",
"use_cache": true,
"vocab_size": 32000
}

7
generation_config.json Normal file
View File

@@ -0,0 +1,7 @@
{
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 0,
"transformers_version": "4.29.2"
}

42
mamba_gpt_pipeline.py Normal file
View File

@@ -0,0 +1,42 @@
from transformers import TextGenerationPipeline
from transformers.pipelines.text_generation import ReturnType
STYLE = "<|prompt|>{instruction}</s><|answer|>"
class MambaGPTTextGenerationPipeline(TextGenerationPipeline):
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)
self.prompt = STYLE
def preprocess(
self, prompt_text, prefix="", handle_long_generation=None, **generate_kwargs
):
prompt_text = self.prompt.format(instruction=prompt_text)
return super().preprocess(
prompt_text,
prefix=prefix,
handle_long_generation=handle_long_generation,
**generate_kwargs,
)
def postprocess(
self,
model_outputs,
return_type=ReturnType.FULL_TEXT,
clean_up_tokenization_spaces=True,
):
records = super().postprocess(
model_outputs,
return_type=return_type,
clean_up_tokenization_spaces=clean_up_tokenization_spaces,
)
for rec in records:
rec["generated_text"] = (
rec["generated_text"]
.split("<|answer|>")[1]
.strip()
.split("<|prompt|>")[0]
.strip()
)
return records

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b4fe205eea08add7a00632634f3501814eea3c118ef400feaba0eb50e4f4ecb9
size 6852982288

3
pytorch_model.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:61bfe8e444206ea7341123d9b1e125955b94efd240016e75c5664271bdde92c0
size 6853041741

26
special_tokens_map.json Normal file
View File

@@ -0,0 +1,26 @@
{
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"cls_token": "</s>",
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"pad_token": "</s>",
"sep_token": "</s>",
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

3
tokenizer.model Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:81c4a3c9a9bbad64636d93660b6982940cec979a398f42684ba7194d118a3f21
size 534194

34
tokenizer_config.json Normal file
View File

@@ -0,0 +1,34 @@
{
"add_bos_token": true,
"add_eos_token": false,
"add_prefix_space": false,
"bos_token": {
"__type": "AddedToken",
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"clean_up_tokenization_spaces": false,
"eos_token": {
"__type": "AddedToken",
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"model_max_length": 2048,
"pad_token": null,
"sp_model_kwargs": {},
"tokenizer_class": "LlamaTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}